Browse by author
Lookup NU author(s): Professor Paul WatsonORCiD,
Professor Savas Parastatidis
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
This paper describes a new runtime technique for lazily exploiting parallelism in iterative and recursive computations. The technique is based around the Tasklet, a construct used to represent a task that could be executed in parallel if that is necessary to keep the system busy, or inline if not. The major advantage of this technique, when compared to previous schemes, is that only one Tasklet is created for a whole iterative or recursive computation, rather than one for each iteration of a loop or for every potentially parallel call in a recursion. The techniques are used by NIP [1,2], a runtime system for parallel platforms (including networks of workstations), that supports implicitly parallel languages combining both functional and object-oriented programming. In the paper, the design and usage of Tasklets is described, and performance results presented.
Author(s): Watson P; Parastatidis S
Editor(s): Arabnia, HR
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: International Conference on Parallel and Distributed Processing Techniques and Applications
Year of Conference: 1999
Publisher: CSREA Press
Library holdings: Search Newcastle University Library for this item
Series Title: INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOLS I-V, PROCEEDINGS